Domain-Guided Task Decomposition with Self-Training for Detecting Personal Events in Social Media
This addresses the challenge of lexical sparsity and data scarcity in social media mining for tasks such as health mention detection, offering an incremental improvement in classification performance.
The paper tackled the problem of detecting personal events in social media by proposing a two-step approach involving domain-guided task decomposition and self-training, which outperformed state-of-the-art models like BERT when limited training data was available.
Mining social media content for tasks such as detecting personal experiences or events, suffer from lexical sparsity, insufficient training data, and inventive lexicons. To reduce the burden of creating extensive labeled data and improve classification performance, we propose to perform these tasks in two steps: 1. Decomposing the task into domain-specific sub-tasks by identifying key concepts, thus utilizing human domain understanding; and 2. Combining the results of learners for each key concept using co-training to reduce the requirements for labeled training data. We empirically show the effectiveness and generality of our approach, Co-Decomp, using three representative social media mining tasks, namely Personal Health Mention detection, Crisis Report detection, and Adverse Drug Reaction monitoring. The experiments show that our model is able to outperform the state-of-the-art text classification models--including those using the recently introduced BERT model--when small amounts of training data are available.